{"id":"https://openalex.org/W3212321533","doi":"https://doi.org/10.1109/mlsp52302.2021.9596389","title":"Detecting Cover Songs with Pitch Class Key-Invariant Networks","display_name":"Detecting Cover Songs with Pitch Class Key-Invariant Networks","publication_year":2021,"publication_date":"2021-10-25","ids":{"openalex":"https://openalex.org/W3212321533","doi":"https://doi.org/10.1109/mlsp52302.2021.9596389","mag":"3212321533"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp52302.2021.9596389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp52302.2021.9596389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005665018","display_name":"Ken O\u2019Hanlon","orcid":"https://orcid.org/0000-0001-8562-6608"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Ken O'Hanlon","raw_affiliation_strings":["Centre for Digital Music, Queen Mary University of London, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084672392","display_name":"Emmanouil Benetos","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":["Centre for Digital Music, Queen Mary University of London, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077484271","display_name":"Simon Dixon","orcid":"https://orcid.org/0000-0002-6098-481X"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon Dixon","raw_affiliation_strings":["Centre for Digital Music, Queen Mary University of London, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005665018"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":0.4628,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62892114,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.6764418482780457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6687638759613037},{"id":"https://openalex.org/keywords/octave","display_name":"Octave (electronics)","score":0.5696296095848083},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5647003650665283},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5344858169555664},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.5245016813278198},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48181262612342834},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.445451557636261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4346790015697479},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4276142716407776},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39879876375198364},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19501838088035583},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13290107250213623},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0665392279624939}],"concepts":[{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.6764418482780457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6687638759613037},{"id":"https://openalex.org/C85841341","wikidata":"https://www.wikidata.org/wiki/Q1135984","display_name":"Octave (electronics)","level":2,"score":0.5696296095848083},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5647003650665283},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5344858169555664},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.5245016813278198},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48181262612342834},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.445451557636261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4346790015697479},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4276142716407776},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39879876375198364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19501838088035583},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13290107250213623},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0665392279624939},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mlsp52302.2021.9596389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp52302.2021.9596389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/74336","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/74336","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8175134172","display_name":"Development of Next-Generation Music Recognition Algorithm for Content Monitoring","funder_award_id":"30863","funder_id":"https://openalex.org/F4320335087","funder_display_name":"Innovate UK"}],"funders":[{"id":"https://openalex.org/F4320335087","display_name":"Innovate UK","ror":"https://ror.org/05ar5fy68"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1486009449","https://openalex.org/W2025763800","https://openalex.org/W2076608692","https://openalex.org/W2131739315","https://openalex.org/W2137319814","https://openalex.org/W2154473523","https://openalex.org/W2191779130","https://openalex.org/W2394827912","https://openalex.org/W2402047267","https://openalex.org/W2408482937","https://openalex.org/W2520774990","https://openalex.org/W2752782242","https://openalex.org/W2771265026","https://openalex.org/W2773294482","https://openalex.org/W2807400584","https://openalex.org/W2808779432","https://openalex.org/W2896276533","https://openalex.org/W2949542407","https://openalex.org/W2962701080","https://openalex.org/W2962968281","https://openalex.org/W2963420686","https://openalex.org/W2964083190","https://openalex.org/W2990026565","https://openalex.org/W2991362318","https://openalex.org/W2991402284","https://openalex.org/W3015271757","https://openalex.org/W3015666964","https://openalex.org/W3015847222","https://openalex.org/W3015962533","https://openalex.org/W3016120414","https://openalex.org/W3157005300","https://openalex.org/W3161928252","https://openalex.org/W6682527865","https://openalex.org/W6712631718","https://openalex.org/W6712692208","https://openalex.org/W6714078465","https://openalex.org/W6741791332","https://openalex.org/W6746411809","https://openalex.org/W6746836464","https://openalex.org/W6763771824","https://openalex.org/W6764992649","https://openalex.org/W6771324532","https://openalex.org/W6776393882"],"related_works":["https://openalex.org/W3006286228","https://openalex.org/W2010451527","https://openalex.org/W2002366964","https://openalex.org/W3159174161","https://openalex.org/W2085126320","https://openalex.org/W4249094544","https://openalex.org/W2045090381","https://openalex.org/W4232403550","https://openalex.org/W623607250","https://openalex.org/W3196064807"],"abstract_inverted_index":{"Deep":[0],"Learning":[1],"(DL)":[2],"has":[3],"recently":[4],"been":[5,29],"applied":[6],"successfully":[7],"to":[8,83,123],"the":[9,124],"task":[10],"of":[11,119,132],"Cover":[12],"Song":[13],"Identification":[14],"(CSI).":[15],"Meanwhile,":[16],"neural":[17],"networks":[18],"that":[19,72,100],"consider":[20],"music":[21],"signal":[22],"data":[23,113],"structure":[24],"in":[25],"their":[26],"design":[27],"have":[28],"developed.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34],"propose":[35,95],"a":[36,51,65,102,130],"Pitch":[37],"Class":[38],"Key-Invariant":[39],"Network,":[40],"PiCKINet,":[41],"for":[42],"CSI.":[43],"Like":[44],"some":[45],"other":[46,58,90],"CSI":[47],"networks,":[48,60],"PiCKINet":[49,76,80],"inputs":[50],"Constant-Q":[52],"Transform":[53],"(CQT)":[54],"pitch":[55,69],"feature.":[56],"Unlike":[57],"such":[59],"large":[61],"multi-octave":[62],"kernels":[63],"produce":[64],"latent":[66],"representation":[67],"with":[68],"class":[70],"dimensions":[71],"are":[73],"maintained":[74],"throughout":[75],"by":[77],"key-invariant":[78],"convolutions.":[79],"is":[81],"seen":[82],"be":[84],"more":[85],"effective,":[86],"and":[87,107,110],"efficient,":[88],"than":[89],"CQT-based":[91],"networks.":[92],"We":[93],"also":[94],"an":[96,117],"extended":[97],"variant,":[98],"PiCKINet+,":[99],"employs":[101],"centre":[103],"loss":[104],"penalty,":[105],"squeeze":[106],"excite":[108],"units,":[109],"octave":[111],"swapping":[112],"augmentation.":[114],"PiCKINet+":[115],"shows":[116],"improvement":[118],"~17%":[120],"MAP":[121],"relative":[122],"well-known":[125],"CQTNet":[126],"when":[127],"tested":[128],"on":[129],"set":[131],"~16K":[133],"tracks.":[134]},"counts_by_year":[{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}